以下是一个简单的示例,展示了如何使用 PyTorch 处理自定义图像分类数据集:
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torchvision.datasets import ImageFolder# 数据预处理
transform = transforms.Compose([transforms.Resize((64, 64)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])# 创建 ImageFolder 数据集实例
train_dataset = ImageFolder(root='path/to/dataset', transform=transform)# 创建数据加载器
batch_size = 64
data_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)# 定义简单的卷积神经网络模型
class SimpleCNN(nn.Module):def __init__(self):super(SimpleCNN, self).__init__()self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)self.relu = nn.ReLU()self.pool = nn.MaxPool2d(kernel_size=2, stride=2)self.flatten = nn.Flatten()self.fc1 = nn.Linear(32*32*32, 128)self.fc2 = nn.Linear(128, len(train_dataset.classes)) # 类别数根据数据集自动调整def forward(self, x):x = self.conv1(x)x = self.relu(x)x = self.pool(x)x = self.flatten(x)x = self.fc1(x)x = self.relu(x)x = self.fc2(x)return x# 初始化模型、损失函数和优化器
model = SimpleCNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)# 训练模型
num_epochs = 5
for epoch in range(num_epochs):for images, labels in data_loader:optimizer.zero_grad()outputs = model(images)loss = criterion(outputs, labels)loss.backward()optimizer.step()print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')# 保存模型
torch.save(model.state_dict(), 'custom_classifier_model.pth')# 测试模型
model.eval()
correct = 0
total = 0
with torch.no_grad():for images, labels in data_loader:outputs = model(images)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()print(f'Accuracy on the test images: {100 * correct / total:.2f}%')
这里使用了 ImageFolder
数据集类,它会自动根据文件夹结构为每个类别分配标签。请替换 'path/to/dataset'
为你实际的数据集路径。这样,你就无需手动指定文件路径和标签,代码会自动从文件夹结构中获取这些信息。